> ## Documentation Index
> Fetch the complete documentation index at: https://praison.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Run

> Execute PraisonAI agents from the command line

## Run from agents.yaml

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
praisonai
```

Runs the agents defined in `agents.yaml` in the current directory.

Also works with `python -m praisonai` for users in venvs without an entry-point shim.

## Run with Direct Prompt

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
praisonai "What is machine learning?"
```

No `agents.yaml` needed — answers directly.

Alternatively: `python -m praisonai "What is machine learning?"`

## Run with Auto Mode

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
python -m praisonai --auto "write a blog post about AI"
```

Auto-generates agents and runs them in one step.

## Run with Different Framework

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
# CrewAI
python -m praisonai --framework crewai

# AG2 (AutoGen)
python -m praisonai --framework autogen

# Google ADK
python -m praisonai --framework google_adk
```

## Common Options

| Flag             | Description                                                                               |
| :--------------- | :---------------------------------------------------------------------------------------- |
| `--framework`    | Use `crewai`, `autogen`, `langgraph`, `openai_agents`, or `google_adk` instead of default |
| `--auto "topic"` | Auto-generate and run agents                                                              |
| `--init "topic"` | Generate agents.yaml only                                                                 |
| `--verbose`      | Show detailed output                                                                      |